Machine learning in mental health: a scoping review of methods and applications

Abstract

BackgroundThis paper aims to synthesise the literature on machine learning (ML) and big data applications for mental health, highlighting current research and applications in practice.MethodsWe employed a scoping review methodology to rapidly map the field of ML in mental health. Eight health and information technology research databases were searched for papers covering this domain. Articles were assessed by two reviewers, and data were extracted on the article's mental health application, ML technique, data type, and study results. Articles were then synthesised via narrative review.ResultsThree hundred papers focusing on the application of ML to mental health were identified. Four main application domains emerged in the literature, including: (i) detection and diagnosis; (ii) prognosis, treatment and support; (iii) public health, and; (iv) research and clinical administration. The most common mental health conditions addressed included depression, schizophrenia, and Alzheimer's disease. ML techniques used included support vector machines, decision trees, neural networks, latent Dirichlet allocation, and clustering.ConclusionsOverall, the application of ML to mental health has demonstrated a range of benefits across the areas of diagnosis, treatment and support, research, and clinical administration. With the majority of studies identified focusing on the detection and diagnosis of mental health conditions, it is evident that there is significant room for the application of ML to other areas of psychology and mental health. The challenges of using ML techniques are discussed, as well as opportunities to improve and advance the field.

Social Media and Mental Health: Benefits, Risks, and Opportunities for Research and Practice

“…Given that most people access social media via mobile devices, digital phenotyping and social media are closely related (Torous et al 2019). To date, the emergence of machine learning, a powerful computational method involving statistical and mathematical algorithms (Shatte et al 2019), has made it possible to study large quantities of data captured from popular social media platforms such as Twitter or Instagram to illuminate various features of mental health (Manikonda and De Choudhury 2017;. Specifically, conversations on Twitter have been analyzed to characterize the onset of depression (De Choudhury et al 2013) as well as detecting users' mood and affective states (De Choudhury et al 2012), while photos posted to Instagram can yield insights for predicting depression .…”

Subtypes in patients with opioid misuse: A prognostic enrichment strategy using electronic health record data in hospitalized patients

“…Latent Dirichlet Allocation (LDA) is an unsupervised text mining approach used for topic modeling [32]. The LDA model was trained on the full cohort of patients with opioid misuse and produced topics expressed as a probability distribution over CUIs.…”

Ethical dilemmas posed by mobile health and machine learning in psychiatry research

“…Machine learning is being increasingly applied in psychiatry for diagnosis, treatment selection and clinical administration. 32,33 However, its future is affected by a key ethical dilemma associated with the trade-off between the performance and the interpretability of machine learning models. Interpretability relates to the ease of deciphering how a set of inputs to a model (e.g.…”